Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Dream Machine API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Flumalabs.ai%2Flumalabs" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Flumalabs.ai%2Flumalabs" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Dream Machine API.
Generate a video from a text or image prompt
Generate an image from a prompt
Upscale a completed generation to higher resolution
Reframe a video or image to a new aspect ratio
Add audio to a generation or modify an existing video
GET STARTED
Check the remaining credits before starting a job
Patterns agents use Dream Machine API for, with concrete tasks.
★ Generate video for an AI agent workflow
An AI agent integration created through Jentic turns a prompt into a finished clip. The Dream Machine API creates a video generation, exposes the generation to poll until it is ready, and can upscale or add audio afterwards, so the agent produces and refines video without the developer wiring the generation lifecycle by hand.
Create a video generation from a prompt, poll until it completes, then upscale the result
Produce marketing images on demand
A campaign needs images generated to a brief. The Dream Machine API generates an image from a prompt and can reframe it to the aspect ratio a channel requires, so an automation produces on-brand visuals and adapts them for different placements from a single request flow.
Generate an image from a prompt and reframe it to a 9:16 aspect ratio
Add sound to generated video
Silent generated clips often need an audio track. The Dream Machine API adds audio to a generation and can modify an existing video, so an agent can take a completed clip and produce a sound-enabled or edited version without re-generating from scratch.
Add audio to a completed video generation and retrieve the updated result
13 endpoints — the dream machine api generates videos and images from text and image prompts, then refines the results.
METHOD
PATH
DESCRIPTION
/generations/video
Create a video generation
/generations/image
Generate an image
/generations/{id}/upscale
Upscale a generation
/generations/{id}/audio
Add audio to a generation
/generations/video/reframe
Reframe a video
/generations/{id}
Get a generation
/credits
Get remaining credits
/generations/video
Create a video generation
/generations/image
Generate an image
/generations/{id}/upscale
Upscale a generation
/generations/{id}/audio
Add audio to a generation
/generations/video/reframe
Reframe a video
/generations/{id}
Get a generation
/credits
Get remaining credits
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Dream Machine API by hand means handling its bearer token and polling each generation until it finishes before you can upscale or add audio. Through Jentic you install once, import Dream Machine from the API Directory, store the token once, and your agent calls it.
Permission scoping
Dream Machine puts the generation id in the URL path for the detail, upscale, and audio operations, so a rule can limit your agent to creating and refining generations. You choose the operations it may call, so deleting a generation is not included unless you add it.
Credential isolation
Your Dream Machine token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'generate a video from a prompt' or 'upscale a generation', and Jentic returns the matching Dream Machine operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Dream Machine API through Jentic.
What authentication does the Dream Machine API use?
The Dream Machine API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.
Can I generate a video from a prompt with the Dream Machine API?
Yes. The video generation operation starts a job from a text or image prompt, and you retrieve the generation to poll until it is ready, after which you can upscale it or add audio.
Can I check my remaining credits with the Dream Machine API?
Yes. The credits operation returns the remaining balance on the account, so an agent can confirm there is enough credit before starting a generation and avoid failed jobs.
How do I generate a video through Jentic?
Install Jentic One on your own infrastructure with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import the Dream Machine API from the API Directory and search for 'generate a video from a text prompt'. Store the token once and your agent can create and refine generations. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Dream Machine MCP server?
You don't need an MCP server to give your agent the Dream Machine API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls it, with operations discovered on demand instead of loaded into the agent's context.
Can I limit what my agent is allowed to do with the Dream Machine API?
Yes. The generation id sits in the URL path for the detail, upscale, and audio operations, so a rule can scope the agent to creating and refining generations while deletion stays out of reach unless you add it. Every action it takes is recorded in an audit log.
For Agents
Generate videos and images from prompts with Luma's Dream Machine, then upscale, reframe, modify, and add audio to the results.
Use for: Generate a video from a text prompt, Create an image from a prompt, Upscale a finished generation, Reframe a video to a new aspect ratio
Not supported: Does not handle text generation, image hosting, or video streaming. Use for generating and editing video and image media only.
The Dream Machine API generates videos and images from text and image prompts, then refines the results. It lets you create a video or image generation, list and retrieve generations, upscale a finished result, reframe a video or image to a new aspect ratio, modify a video, and add audio, with a credits endpoint to check your balance. Requests are authenticated with a bearer token.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>